hardware-health-check
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external BMC components, creating an attack surface where malicious data could influence agent behavior.
- Ingestion points: Data entering the context includes
redfish_logs(event logs) andredfish_firmware(firmware inventory metadata) as described in the SKILL.md workflows. - Boundary markers: The skill does not provide specific instructions or delimiters to the agent to separate untrusted external data from the agent's core instructions.
- Capability inventory: The skill provides read-only access to several BMC data sources via tools including
redfish_status,redfish_systems, andredfish_logs, but explicitly excludes power control or reset commands. - Sanitization: No explicit validation or filtering of the data returned by the Redfish tools is documented.
Audit Metadata